​
Code

cookbook/models/cerebras/basic_json_schema.py
from typing import List

from agno.agent import Agent, RunResponse  # noqa
from agno.models.cerebras import Cerebras
from pydantic import BaseModel, Field
from rich.pretty import pprint  # noqa

class MovieScript(BaseModel):
    setting: str = Field(
        ..., description="提供一个精彩的卖座电影的场景。"
    )
    ending: str = Field(
        ...,
        description="电影结局。如果不可用，请提供一个圆满结局。",
    )
    genre: str = Field(
        ...,
        description="电影类型。如果不可用，请选择动作、惊悚或浪漫喜剧。",
    )
    name: str = Field(..., description="给这部电影起个名字")
    characters: List[str] = Field(..., description="这部电影的角色名字。")
    storyline: str = Field(
        ..., description="电影的故事梗概，三句话。要令人兴奋！"
    )

# Agent that uses a JSON schema output
json_schema_output_agent = Agent(
    model=Cerebras(id="llama-4-scout-17b-16e-instruct"),
    description="你是一个乐于助人的助手。根据地点总结电影剧本，并将其放入一个 JSON 对象。",
    response_model=MovieScript,
)

json_schema_output_agent.print_response("New York")

​
Usage

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

设置你的 API 密钥

export CEREBRAS_API_KEY=xxx
3

安装库

pip install -U cerebras-cloud-sdk agno
4

运行 Agent

python cookbook/models/cerebras/basic_json_schema.py